© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 14502
    Prev
    Next
    INDEX
    Explanations

    descriptions of initiatives related to educational or community programs

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     Efq
    -0.86
     chofe
    -0.79
    IBarButtonItem
    -0.73
    تقاوى
    -0.72
     poffe
    -0.72
     neceff
    -0.70
    CloseOperation
    -0.70
    ThroughAttribute
    -0.68
    contentLoaded
    -0.68
    styleType
    -0.67
    POSITIVE LOGITS
     initiative
    1.13
     Initiative
    0.94
     program
    0.91
     initiatives
    0.90
    Initiative
    0.89
     programme
    0.88
     iniciativa
    0.87
     project
    0.82
    initiative
    0.81
     Project
    0.77
    Activations Density 0.144%

    No Known Activations